提出新型神经网络模型，高效模拟高温下镁合金的各向异性塑性行为。
Temperature-Aware Recurrent Neural Operator for Temperature-Dependent Anisotropic Plasticity in HCP Materials
- 设计时间无关的温度感知递归神经算子，提升建模泛化能力
- 在多种温度与加载条件下预测准确率高，训练效率超传统GRU/LSTM
- 适用于多尺度仿真，速度比传统方法快至少1000倍
用于计算力学中本构关系的神经网络代理模型已广泛应用。在塑性领域，这类模型通常依赖门控循环单元（GRUs）或长短期记忆（LSTM）单元，能有效捕捉路径依赖现象，但存在训练时间长、时间分辨率依赖性强、外推性能差等问题。此外，现有宏观或介观塑性代理模型大多仅适用于较简单的材料行为。为克服上述局限，本文提出温度感知递归神经算子（TRNO），一种时间分辨率无关的神经架构。将TRNO应用于多晶镁的温度依赖塑性响应建模，该材料具有显著的塑性各向异性和热敏感性。TRNO在不同加载条件、温度和时间分辨率下均实现高精度预测，并展现出优异的泛化能力，且在训练效率和预测性能上优于传统GRU和LSTM模型。最后，基于TRNO的多尺度仿真实现了至少三个数量级的速度提升，相较传统本构模型大幅加速。
原文摘要 · Abstract (English)
Neural network surrogate models for constitutive laws in computational mechanics have been in use for some time. In plasticity, these models often rely on gated recurrent units (GRUs) or long short-term memory (LSTM) cells, which excel at capturing path-dependent phenomena. However, they suffer from long training times and time-resolution-dependent predictions that extrapolate poorly. Moreover, most existing surrogates for macro- or mesoscopic plasticity handle only relatively simple material behavior. To overcome these limitations, we introduce the Temperature-Aware Recurrent Neural Operator (TRNO), a time-resolution-independent neural architecture. We apply the TRNO to model the temperature-dependent plastic response of polycrystalline magnesium, which shows strong plastic anisotropy and thermal sensitivity. The TRNO achieves high predictive accuracy and generalizes effectively across diverse loading cases, temperatures, and time resolutions. It also outperforms conventional GRU and LSTM models in training efficiency and predictive performance. Finally, we demonstrate multiscale simulations with the TRNO, yielding a speedup of at least three orders of magnitude over traditional constitutive models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。